arXiv AI By Ghislain Dorian Tchuente Mondjo

Budget-First Tariff Recommendation (BFTR): A Complete Algorithmic Framework for Telecom Plan Recommendation without Overcharging

Read the original on arXiv AI →

The paper introduces Budget-First Tariff Recommendation (BFTR), an algorithmic framework that offers telecom plans without overcharging by aligning final prices with catalog reference prices. BFTR incorporates eight Budget-First strategies, including two novel hybrid approaches—Recursive Hybrid and Knapsack-First Hybrid— and mathematically proves that a suitable offer exists for any positive budget with zero surcharge for non‑interpolated strategies. Experiments on a Nigerian MTN‑inspired dataset show that all strategies achieve zero overcharging, with Recursive Hybrid delivering optimal customer utility and Piecewise maximizing volume, while maintaining sub‑10 ms execution times.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers
Aug 19

Budget-First Tariff Recommendation (BFTR): A Complete Algorithmic Framework for Telecom Plan Recommendation without Overcharging

The paper introduces BFTR, a Budget‑First Tariff Recommendation framework that offers eight algorithmic strategies, including two novel hybrid approaches (Recursive Hybrid and Knapsack‑First Hybrid). It mathematically guarantees no overcharging by aligning final prices with catalog reference prices and proves that a suitable offer exists for any positive budget. Experiments on 974 Nigerian MTN customers show all strategies achieve zero surcharge, with Recursive Hybrid and Piecewise delivering optimal budget usage and volume, respectively, while maintaining sub‑10 ms execution times.